Align default-branch wording and question guidance

docs/macos.md

@@ -27,7 +27,7 @@ Every build is signed for distribution outside the App Store: the team's Develop
 ## Startup and streams
 
 - Startup waits until the app's tailnet node lists the server's node among its peers, not just until it is `Running`: a node starting from libtailscale's netmap cache reports `Running` with no peers before control sends the real netmap, and a dial then waits out the SOCKS proxy's 5 s and is refused, which `URLSession` reports as "bad URL".
-- The SSE client splits lines itself, because `AsyncBytes.lines` drops the blank lines that end SSE events.
+- `AsyncBytes.lines` drops blank lines, including the ones that end SSE events.
 - Run byre on this Mac and the Server tab run `byre install` through the user's login shell, since `byre install` copies its `PATH` into the service and the app's own `PATH` from launchd finds none of `claude`, `codex`, `agy` or `npx`.
 - SwiftUI's window restoration is off, but the scene keeps the id `main` that earlier builds used: AppKit restores their saved window by that id, and SwiftUI then opens no launch window at all when the id names no scene.
 - The app logs through `os.Logger`: `log show --last 10m --predicate 'subsystem == "run.fc.byre.mac"'` prints it.

docs/operations.md

@@ -71,7 +71,6 @@ Vendor setup and protocol quirks are in [Claude Code](claude-protocol.md), [Code
 
 - Every agent CLI starts in its own process group, and killing one kills the whole group. Otherwise a launcher that runs the real agent as its child, along with the agent's MCP servers, can keep holding byre's stdout pipe, and the kill waits forever for end of file.
 - Codex runs with its own home, `codex` under the data directory (`CODEX_HOME`), so the human's `~/.codex/config.toml` (its `notify` program, MCP servers and plugins) doesn't apply and byre's threads stay out of the ChatGPT app's history. That home needs its own login, once: `CODEX_HOME="$HOME/Library/Application Support/byre/codex" codex login`. Until then a Codex turn fails with `401 Unauthorized`, filed as a session error.
-- Codex's stdout reader blocks when its event consumer falls behind, so responses queued behind those notifications wait too: the goroutine draining events therefore never waits on a reply itself.
 - Antigravity uses the user's own login and config (`~/.gemini`), so its conversations show up in the user's own `agy` history.
 - Claude Code records `--append-system-prompt` on a session's first request and reuses it on resume, so a running session keeps the guidance it started with; the `UserPromptSubmit` hook re-attaches the guidance to every turn so existing sessions see changes. On a fork Claude Code can reuse the system prompt recorded for the source conversation, the source's cwd included, so the hook's copy is what reliably tells a fork where it is.
 - A Claude `result` with `num_turns` 0, no `result` text and no error, outside an interrupt, isn't a turn end: the CLI emits one on its own, for example after a resume when it reports a background shell left over from the previous process. byre logs `ignored result with no model turns` and keeps the turn running.
@@ -81,7 +80,7 @@ Vendor setup and protocol quirks are in [Claude Code](claude-protocol.md), [Code
 ## Agent behavior
 
 - A turn whose final message asks the human something in prose is bounced once, telling the agent to use `ask_human`. For Claude the bounce is a Stop hook that blocks the stop; Claude Code reports the block as a "Stop hook error" notification, which is expected. An agent told explicitly to ask in plain text will refuse the bounce.
-- A turn's final message is its summary. There is no report tool: models write a closing recap whatever they are told, so byre uses it rather than asking for a second one.
+- A turn that asks a question has no summary; everything the human needs belongs in the question's context. Other turns use their final message as the summary. There is no report tool: models already write a closing recap, so byre uses it rather than asking for a second one.
 - A review covers the whole task against the default branch, so a newer one makes older ones moot. Findings reach the task's agent together, once the whole review workflow finishes; an individual reviewer finishing is not a completed review.
 - An audit checks only the newest commit of the default branch, one at a time per project, so it doesn't run on every revision but the newest one is always audited eventually. byre never fetches for an audit, so a commit pushed outside byre is audited only once a byre merge has fetched it.
 - The lead's `show` is refused for a few seconds after the human moves the pane, and only a refusal arranges the "hold is over" signal, so the lead's prompt tells it to call `show` at once whenever it wants to show something, never holding back in expectation of a refusal.